Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prior art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     economy
    -0.07
     Lonely
    -0.07
     Unique
    -0.06
     Loop
    -0.06
     」
    -0.06
    言葉
    -0.06
    SAVE
    -0.06
    Testing
    -0.06
     ，
    -0.06
     Linux
    -0.06
    POSITIVE LOGITS
    ху
    0.06
     giao
    0.06
    .BackgroundColor
    0.06
    247
    0.06
     ect
    0.06
    有点
    0.06
     Бі
    0.06
     ابن
    0.06
     نام
    0.06
    derive
    0.06
    Act Density 0.030%

    No Known Activations